© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 38363
    Prev
    Next
    INDEX
    Explanations

    Grammar/writing modifications

    np_max-act · gemini-2.0-flash

    This neuron activates on the instruction specifying the “jailbreak” prefix (e.g. “[JAILBREAK]” and its surrounding context, like “in front of …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    but
    -0.07
    ButtonItem
    -0.07
    Developer
    -0.07
    _keyboard
    -0.06
     Saunders
    -0.06
     recreated
    -0.06
     Algorithm
    -0.06
    /design
    -0.06
     Therefore
    -0.06
     uf
    -0.06
    POSITIVE LOGITS
     вос
    0.06
    侵
    0.06
    sono
    0.06
    ään
    0.06
     Єв
    0.06
    .Warn
    0.06
    theValue
    0.06
     奥
    0.06
    전자
    0.06
    CEF
    0.06
    Activations Density 0.001%

    No Known Activations